In this paper we present a plan-plan distance metric based on Kolmogorov(Algorithmic) complexity. Generating diverse sets of plans is useful for task ssuch as probing user preferences and reasoning about vulnerability to cyberattacks. Generating diverse plans, and comparing different diverse planning approaches requires a domain-independent, theoretically motivated definition of the diversity distance between plans. Previously proposed diversity measures are not theoretically motivated, and can provide inconsistent results on the sameplans. We define the diversity of plans in terms of how surprising one plan is givenanother or, its inverse, the conditional information in one plan givenanother. Kolmogorov complexity provides a domain independent theory of conditional information. While Kolmogorov complexity is not computable, a related metric, Normalized Compression Distance (NCD), provides a well-behaved approximation. In this paper we introduce NCD as an alternative diversity metric, and analyze its performance empirically, in comparison with previous diversity measures, showing strengths and weaknesses of each.We also examine the use of different compressor sin NCD. We show how NCD can be used to select a training set for HTN learning,giving an example of the utility of diversity metrics. We conclude withsuggestions for future work on improving, extending, and applying it to serve new applications.

Algorithmic reductions are one of the corner stones of theoretical computer science. Surprisingly, to-date, they have only played a limited role in machine learning. In this paper we introduce a formal and practical reduction between two of the most widely used machine learning algorithms: from the Elastic Net (and the Lasso as a special case) to the Support Vector Machine. First, we derive the reduction and summarize it in only 11 lines of MATLAB. Then, we demonstrate its high impact potential by translating recent advances in parallelizing SVM solvers directly to the Elastic Net. The resulting algorithm is a parallel solver for the Elastic Net (and Lasso) that naturally utilizes GPU and multi-core CPUs. We evaluate it on twelve real world data sets, and show that it yields identical results as the popular (and highly optimized) glmnet implementation but is up-to two orders of magnitude faster.

Matrix factorization (MF) has been attracting much attention due to its wide applications. However, since MF models are generally non-convex, most of the existing methods are easily stuck into bad local minima, especially in the presence of outliers and missing data. To alleviate this deficiency, in this study we present a new MF learning methodology by gradually including matrix elements into MF training from easy to complex. This corresponds to a recently proposed learning fashion called self-paced learning (SPL), which has been demonstrated to be beneficial in avoiding bad local minima. We also generalize the conventional binary (hard) weighting scheme for SPL to a more effective real-valued (soft) weighting manner. The effectiveness of the proposed self-paced MF method is substantiated by a series of experiments on synthetic, structure from motion and background subtraction data.

In online bandit learning, the learner aims to minimize a sequence of losses, while only observing the value of each loss at a single point. Although various algorithms and theories have been developed for online bandit learning, most of them are limited to convex losses. In this paper, we investigate the problem of online bandit learning with non-convex losses, and develop an efficient algorithm with formal theoretical guarantees. To be specific, we consider a class of losses which is a composition of a non-increasing scalar function and a linear function. This setting models a wide range of supervised learning applications such as online classification with a non-convex loss. Theoretical analysis shows that our algorithm achieves an O(poly(d)T2/3) regret bound when the variation of the loss function is small. To the best of our knowledge, this is the first work in online bandit learning that does not rely on convexity.

Locality preserving projection (LPP) is an effective dimensionality reduction method based on manifold learning, which is defined over the graph weighted squared L2-norm distances in the projected subspace. Since squared L2-norm distance is prone to outliers, it is desirable to develop a robust LPP method. In this paper, motivated by existing studies that improve the robustness of statistical learning models via L1-norm or not-squared L2-norm formulations, we propose a robust LPP (rLPP) formulation to minimize the p-th order of the L2-norm distances, which can better tolerate large outlying data samples because it suppress the introduced biased more than the L1-norm or not squared L2-norm minimizations. However, solving the formulated objective is very challenging because it not only non-smooth but also non-convex. As an important theoretical contribution of this work, we systematically derive an efficient iterative algorithm to solve the general p-th order L2-norm minimization problem, which, to the best of our knowledge, is solved for the first time in literature. Extensive empirical evaluations on the proposed rLPP method have been performed, in which our new method outperforms the related state-of-the-art methods in a variety of experimental settings and demonstrate its effectiveness in seeking better subspaces on both noiseless and noisy data.

The related problems of transfer learning and multitask learning have attracted significant attention, generating a rich literature of models and algorithms. Yet most existing approaches are studied in an offline fashion, implicitly assuming that data from different domains are given as a batch. Such an assumption is not valid in many real-world applications where data samples arrive sequentially, and one wants a good learner even from few examples. The goal of our work is to provide sound extensions to existing transfer and multitask learning algorithms such that they can be used in an anytime setting. More specifically, we propose two novel online boosting algorithms, one for transfer learning and one for multitask learning, both designed to leverage the knowledge of instances in other domains. The experimental results show state-of-the-art empirical performance on standard benchmarks, and we present results of using our methods for effectively detecting new seizures in patients with epilepsy from very few previous samples.

This paper describes a new information-theoretic policy evaluation technique for reinforcement learning. This technique converts any compression or density model into a corresponding estimate of value. Under appropriate stationarity and ergodicity conditions, we show that the use of a sufficiently powerful model gives rise to a consistent value function estimator. We also study the behavior of this technique when applied to various Atari 2600 video games, where the use of suboptimal modeling techniques is unavoidable. We consider three fundamentally different models, all too limited to perfectly model the dynamics of the system. Remarkably, we find that our technique provides sufficiently accurate value estimates for effective on-policy control. We conclude with a suggestive study highlighting the potential of our technique to scale to large problems.

The traditional way of obtaining models from data, inductive learning, has proved itself both in theory and in many practical applications. However, in domains where data is difficult or expensive to obtain, e.g., medicine, deep transfer learning is a more promising technique. It circumvents the model acquisition difficulties caused by scarce data in a target domain by carrying over structural properties of a model learned in a source domain where training data is ample. Nonetheless, the lack of a principled view of transfer learning so far has limited its adoption. In this paper, we address this issue by regarding transfer learning as a process that biases learning in a target domain in favor of patterns useful in a source domain. Specifically, we consider a first-order logic model of the data as an instantiation of a set of second-order templates. Hence, the usefulness of a model is partly determined by the learner's prior distribution over these template sets. The main insight of our work is that transferring knowledge amounts to acquiring a posterior over the second-order template sets by learning in the source domain and using this posterior when learning in the target setting. Our experimental evaluation demonstrates our approach to outperform the existing transfer learning techniques in terms of accuracy and runtime.

Many reinforcement learning algorithms use trajectories collected from the execution of one or more policies to propose a new policy. Because execution of a bad policy can be costly or dangerous, techniques for evaluating the performance of the new policy without requiring its execution have been of recent interest in industry. Such off-policy evaluation methods, which estimate the performance of a policy using trajectories collected from the execution of other policies, heretofore have not provided confidences regarding the accuracy of their estimates. In this paper we propose an off-policy method for computing a lower confidence bound on the expected return of a policy.

Conditional Value at Risk (CVaR) is a prominent risk measure that is being used extensively in various domains. We develop a new formula for the gradient of the CVaR in the form of a conditional expectation. Based on this formula, we propose a novel sampling-based estimator for the gradient of the CVaR, in the spirit of the likelihood-ratio method. We analyze the bias of the estimator, and prove the convergence of a corresponding stochastic gradient descent algorithm to a local CVaR optimum. Our method allows to consider CVaR optimization in new domains. As an example, we consider a reinforcement learning application, and learn a risk-sensitive controller for the game of Tetris.